INDEX

Explanations

coding references and event-related terms in technical documents

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Phys. Rev. Lett

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rawDesc

-0.49

ApiProperty

-0.48

DispatchToProps

-0.45

DebuggerNonUser

-0.43

 masculinos

-0.40

WriteLiteral

-0.39

vœ

-0.38

 Púb

-0.37

awaiter

-0.36

 Desarrollo

-0.35

POSITIVE LOGITS

 Италијани

0.61

CodeAttribute

0.60

principalTable

0.58

ۜ

0.56

SharedDtor

0.56

 Himo

0.52

 ligiloj

0.50

 Normdatei

0.50

uxxxx

0.50

 OFDb

0.50

Activations Density 0.005%

coding references and event-related terms in technical documents

Phys. Rev. Lett

No Comments

No Known Activations

coding references and event-related terms in technical documents

Phys. Rev. Lett

No Comments

No Known Activations